Forest Fires.ipynb

Kernel: Python 3 (Anaconda)

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
plt.rcParams["figure.figsize"] = (12, 9) # inches
import seaborn as sns; sns.set()

data = pd.read_csv('forestfires.csv', header=0, sep=',')

data.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 517 entries, 0 to 516
Data columns (total 13 columns):
X        517 non-null int64
Y        517 non-null int64
month    517 non-null object
day      517 non-null object
FFMC     517 non-null float64
DMC      517 non-null float64
DC       517 non-null float64
ISI      517 non-null float64
temp     517 non-null float64
RH       517 non-null int64
wind     517 non-null float64
rain     517 non-null float64
area     517 non-null float64
dtypes: float64(8), int64(3), object(2)
memory usage: 52.6+ KB

data.head()

sns.distplot(data['area']);

/ext/anaconda3/lib/python3.5/site-packages/matplotlib/axes/_axes.py:6462: UserWarning: The 'normed' kwarg is deprecated, and has been replaced by the 'density' kwarg.
  warnings.warn("The 'normed' kwarg is deprecated, and has been "

data['area'].value_counts(normalize=True)

0.00     0.477756
1.94     0.005803
3.71     0.003868
0.90     0.003868
1.95     0.003868
2.14     0.003868
2.18     0.003868
1.56     0.003868
9.96     0.003868
28.66    0.003868
1.46     0.003868
0.68     0.003868
0.43     0.003868
1.64     0.003868
6.43     0.003868
9.27     0.003868
0.52     0.003868
1.75     0.003868
11.06    0.003868
1.63     0.003868
17.20    0.001934
48.55    0.001934
0.95     0.001934
0.77     0.001934
11.19    0.001934
15.64    0.001934
2.64     0.001934
3.52     0.001934
38.48    0.001934
5.39     0.001934
           ...   
1.61     0.001934
1.07     0.001934
6.38     0.001934
5.86     0.001934
3.19     0.001934
11.16    0.001934
8.85     0.001934
86.45    0.001934
5.18     0.001934
30.18    0.001934
2.01     0.001934
1.01     0.001934
20.03    0.001934
0.79     0.001934
49.59    0.001934
4.41     0.001934
7.02     0.001934
0.71     0.001934
9.41     0.001934
0.09     0.001934
3.32     0.001934
11.53    0.001934
5.55     0.001934
3.20     0.001934
4.88     0.001934
1.26     0.001934
2.44     0.001934
2.03     0.001934
2.21     0.001934
24.24    0.001934
Name: area, Length: 251, dtype: float64

fig, ax = plt.subplots(1, 3)
sns.violinplot(data['area'], ax=ax[0])
sns.violinplot(np.log(1+data['area']), ax=ax[1])
sns.violinplot(np.log(1+np.log(1+data['area'])), ax=ax[2]);

sns.distplot(np.log(1+data['area']));

/ext/anaconda3/lib/python3.5/site-packages/matplotlib/axes/_axes.py:6462: UserWarning: The 'normed' kwarg is deprecated, and has been replaced by the 'density' kwarg.
  warnings.warn("The 'normed' kwarg is deprecated, and has been "

sns.distplot(np.log(1+np.log(1+data['area'])));

/ext/anaconda3/lib/python3.5/site-packages/matplotlib/axes/_axes.py:6462: UserWarning: The 'normed' kwarg is deprecated, and has been replaced by the 'density' kwarg.
  warnings.warn("The 'normed' kwarg is deprecated, and has been "